Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651

Browse

Filters

20252

Settings

Access Right: Open AccessCOAR Access Rights: search.filters.coarAccessRights.metadata only access

Search Results

Now showing 1 - 2 of 2
  • Conference Object
    AviBERT: Transformer Tabanlı Hava Aracı Metni Sınıflandırma
    (Institute of Electrical and Electronics Engineers Inc., 2025) Unal, Muhammed Cihat; Yurtalan, Gokhan; Karatas, Yahya Bahadir; Karamanlioglu, Alper; Demirel, Berkan
    In recent years, transformer-based models pre-trained on extensive corpora have played a critical role in the advancement of Natural Language Processing methodologies. Particularly, methods based on BERT have demonstrated remarkable performance across various tasks by offering robust capabilities in deeply understanding texts semantically. However, despite these advancements, there is a notable scarcity of studies applying these technologies in the aviation sector. This paper develops a multi-class classification model for aviation-specific texts using variants of BERT. The study encompasses the processes of collecting web content related to aircraft, labeling and model training. The details of the dataset are explained and the outcomes of the study are assessed based on the macro F1-score and accuracy of different models. © 2025 Elsevier B.V., All rights reserved.
  • Article
    Statistical Models for Porous Asphalt Mixtures Containing Pulverized Surface Dressed Pavement Material/Low-density Polyethylene Waste
    (MIM RESEARCH GROUP, 2025) Oner, Julide; Almusawı, Alı; Abdulrahman, Hassan Shuaibu; Ahmed, Nasiru Ibrahim
    Porous asphalt (PA) mixtures typically contain a high proportion of coarse aggregates with minimal fine aggregates, along with a binder that creates ample space for water drainage. Since road construction consumes large quantities of aggregates, recycling and reusing materials have become common practices. This study focuses on developing PA by partially replacing traditional aggregates with pulverized surface-dressed pavement material (PSM) and modifying bitumen with low-density polyethylene (LDPE). The mixtures were produced using 60/70 penetration grade bitumen modified with 2%, 4%, and 6% LDPE waste and 20%, 40%, 60%, and 80% PSM. Adding LDPE waste to the bitumen altered key properties, such as the softening point, penetration, flashpoint, and ductility, resulting in a stiffer binder. Replacing aggregates with PSM reduced both stability and flow, leading to a lower Marshall quotient. Flow values for all trial mixes did not meet AAPA (2004) standards, while stability values slightly decreased as LDPE content increased from 2% to 6%. Despite this, all samples met the AAPA (2004) stability standard. The sample containing 2% LDPE and no PSM exhibited the highest Marshall quotient. Linear regression models were developed from experimental data to highlight the relationships between the measured responses and the variables. These polynomial equations demonstrated a strong correlation, indicated by high coefficients of determination. The study introduces an innovative approach by incorporating PSM and LDPE, largely unexplored in PA production, especially in Nigeria. The major societal benefits include reducing environmental pollution through plastic waste reuse, conserving natural aggregates, and promoting cost-effective construction practices. By advancing the use of recycled materials, this research supports sustainable infrastructure development while maintaining compliance with industry standards. © 2025 MIM Research Group. All rights reserved.